© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92018
    Prev
    Next
    INDEX
    Explanations

    fontawesome, glyphicon, icons

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is keyed to CSS icon class tokens—especially Font Awesome prefixes like “fa”, “fas”, “far”, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dispon
    -0.82
    它
    -0.79
     никто
    -0.79
    îtra
    -0.78
    pruch
    -0.77
    んです
    -0.77
    ことができます
    -0.77
     internetu
    -0.77
    腈
    -0.76
     isEnabled
    -0.75
    POSITIVE LOGITS
     marbre
    0.88
     turquesa
    0.86
     heridos
    0.85
    地面
    0.85
     fa
    0.84
     ailing
    0.83
    ɇ
    0.83
    itars
    0.83
    чны
    0.81
     enfermos
    0.80
    Activations Density 0.002%

    No Known Activations